From a469b8821fe8af760b9aee8b68e89a440cb287e5 Mon Sep 17 00:00:00 2001 From: Jun Siang Cheah Date: Tue, 8 Apr 2025 18:37:29 +0100 Subject: [PATCH] prep gemini 2.5 flash cloud next --- README.md | 37 ++++++++++++++++++++++++++---------- src/pull_available_models.py | 24 +++++++++++++++++++++-- 2 files changed, 49 insertions(+), 12 deletions(-) diff --git a/README.md b/README.md index c241415..76825f1 100644 --- a/README.md +++ b/README.md @@ -23,7 +23,7 @@ This lists various services that provide free access or credits towards API-base -OpenRouter20 requests/minute
50 requests/dayBytedance UI Tars 72B +OpenRouter20 requests/minute
50 requests/dayBytedance UI Tars 72B DeepHermes 3 Llama 3 8B Preview DeepSeek R1 DeepSeek R1 Distill Llama 70B @@ -44,10 +44,13 @@ This lists various services that provide free access or credits towards API-base Gemma 3 4B Instruct Llama 3.1 8B Instruct Llama 3.1 Nemotron 70B Instruct +Llama 3.1 Nemotron Nano 8B v1 +Llama 3.1 Nemotron Ultra 253B v1 Llama 3.2 11B Vision Instruct Llama 3.2 1B Instruct Llama 3.2 3B Instruct Llama 3.3 70B Instruct +Llama 3.3 Nemotron Super 49B v1 Llama 4 Maverick Llama 4 Scout Mistral 7B Instruct @@ -58,9 +61,6 @@ This lists various services that provide free access or credits towards API-base Moonlight-16B-A3B-Instruct OlympicCoder 32B OlympicCoder 7B -OpenChat 7B -Phi-3 Medium 128k Instruct -Phi-3 Mini 128k Instruct Qwen 2.5 72B Instruct Qwen 2.5 7B Instruct Qwen 2.5 VL 32B Instruct @@ -72,14 +72,17 @@ This lists various services that provide free access or credits towards API-base Qwen2.5 VL 72B Instruct Reka Flash 3 Rogue Rose 103B v0.2 -Toppy M 7B Zephyr 7B Beta - Google AI Studio - Data is used for training (when used outside of the UK/CH/EEA/EU). + Google AI Studio + Data is used for training (when used outside of the UK/CH/EEA/EU). Gemini 2.5 Pro (Experimental) 5,000,000 tokens/day
1,000,000 tokens/minute
25 requests/day
5 requests/minute + + Gemini 2.5 Flash (Preview) + + Gemini 2.0 Flash 1,000,000 tokens/minute
1,500 requests/day
15 requests/minute @@ -112,6 +115,14 @@ This lists various services that provide free access or credits towards API-base Gemma 3 27B Instruct 15,000 tokens/minute
14,400 requests/day
30 requests/minute + + Gemma 3 12B Instruct + 15,000 tokens/minute
14,400 requests/day
30 requests/minute + + + Gemma 3 4B Instruct + 15,000 tokens/minute
14,400 requests/day
30 requests/minute + text-embedding-004 150 batch requests/minute
1,500 requests/minute
100 content/batch @@ -246,7 +257,7 @@ This lists various services that provide free access or credits towards API-base Phi-4 Phi-4-mini-instruct Phi-4-multimodal-instruct -ChutesDistributed, decentralized crypto-based compute. Data is sent to individual hosts.DeepHermes 3 Llama 3 8B Preview +ChutesDistributed, decentralized crypto-based compute. Data is sent to individual hosts.DeepHermes 3 Llama 3 8B Preview DeepSeek V3 0324 DeepSeek V3 Base Dolphin 3.0 Mistral 24B @@ -254,6 +265,9 @@ This lists various services that provide free access or credits towards API-base Gemma 3 12B Instruct Gemma 3 1B Instruct Gemma 3 4B Instruct +Llama 3.1 Nemotron Nano 8B v1 +Llama 3.1 Nemotron Ultra 253B v1 +Llama 3.3 Nemotron Super 49B v1 Llama 4 Maverick 17B 128E Instruct FP8 Llama 4 Scout 17B 16E Instruct Mistral Small 3.1 24B Instruct 2503 @@ -407,7 +421,7 @@ This lists various services that provide free access or credits towards API-base Qwen2.5 Coder 32B Instruct Qwen2.5 VL 72B Instruct Qwen2.5 VL 7B Instruct -SambaNova Cloud$5 for 3 monthsE5-Mistral-7B-Instruct +SambaNova Cloud$5 for 3 monthsE5-Mistral-7B-Instruct Llama 3.1 405B Llama 3.1 70B Llama 3.1 8B @@ -416,6 +430,7 @@ This lists various services that provide free access or credits towards API-base Llama 3.2 3B Llama 3.2 90B Vision Llama 3.3 70B +Llama-4-Scout-17B-16E-Instruct Llama-Guard-3-8B Qwen/QwQ-32B Qwen/QwQ-32B-Preview @@ -428,13 +443,15 @@ This lists various services that provide free access or credits towards API-base deepseek-ai/DeepSeek-V3-0324 tokyotech-llm/Llama-3.1-Swallow-70B-Instruct-v0.3 tokyotech-llm/Llama-3.1-Swallow-8B-Instruct-v0.3 -Scaleway Generative APIs1,000,000 free tokensBGE-Multilingual-Gemma2 +Scaleway Generative APIs1,000,000 free tokensBGE-Multilingual-Gemma2 DeepSeek R1 Distill Llama 70B DeepSeek R1 Distill Llama 8B +Gemma 3 27B Instruct Llama 3.1 70B Instruct Llama 3.1 8B Instruct Llama 3.3 70B Instruct Mistral Nemo 2407 +Mistral Small 3.1 24B Instruct 2503 Pixtral 12B (2409) Qwen2.5 Coder 32B Instruct sentence-t5-xxl diff --git a/src/pull_available_models.py b/src/pull_available_models.py index e69c399..e981386 100644 --- a/src/pull_available_models.py +++ b/src/pull_available_models.py @@ -261,6 +261,14 @@ MODEL_TO_NAME_MAPPING = { "nousresearch/deephermes-3-llama-3-8b-preview": "DeepHermes 3 Llama 3 8B Preview", "chutesai/mistral-small-3.1-24b-instruct-2503": "Mistral Small 3.1 24B Instruct 2503", "qwen/qwen2.5-vl-32b-instruct": "Qwen 2.5 VL 32B Instruct", + "nvidia/llama-3_1-nemotron-ultra-253b-v1": "Llama 3.1 Nemotron Ultra 253B v1", + "nvidia/llama-3.1-nemotron-ultra-253b-v1:free": "Llama 3.1 Nemotron Ultra 253B v1", + "nvidia/llama-3.1-nemotron-nano-8b-v1": "Llama 3.1 Nemotron Nano 8B v1", + "mistral-small-3.1-24b-instruct-2503": "Mistral Small 3.1 24B Instruct 2503", + "nvidia/llama-3_3-nemotron-super-49b-v1": "Llama 3.3 Nemotron Super 49B v1", + "gemma-3-27b-it": "Gemma 3 27B Instruct", + "nvidia/llama-3.3-nemotron-super-49b-v1:free": "Llama 3.3 Nemotron Super 49B v1", + "nvidia/llama-3.1-nemotron-nano-8b-v1:free": "Llama 3.1 Nemotron Nano 8B v1", } @@ -942,11 +950,15 @@ def main(): table += "\n" table += f""" - Google AI Studio - Data is used for training (when used outside of the UK/CH/EEA/EU). + Google AI Studio + Data is used for training (when used outside of the UK/CH/EEA/EU). Gemini 2.5 Pro (Experimental) {get_human_limits({"limits": gemini_models["gemini-2.0-pro-exp"]})} + + Gemini 2.5 Flash (Preview) + {get_human_limits({"limits": gemini_models["gemini-2.5-flash-preview"]})} + Gemini 2.0 Flash {get_human_limits({"limits": gemini_models["gemini-2.0-flash"]})} @@ -979,6 +991,14 @@ def main(): Gemma 3 27B Instruct {get_human_limits({"limits": gemini_models["gemma-3-27b"]})} + + Gemma 3 12B Instruct + {get_human_limits({"limits": gemini_models["gemma-3-12b"]})} + + + Gemma 3 4B Instruct + {get_human_limits({"limits": gemini_models["gemma-3-4b"]})} + text-embedding-004 {get_human_limits({"limits": gemini_models["project-embedding"]})}
100 content/batch